Agents got the ability to act before anyone built the thing that decides whether they may. Working on that.
-
code75
- Paris
-
00:20
(UTC -12:00) - www.code75.io
- https://orcid.org/0009-0001-2258-3783
- https://yacine-kellib.github.io/agent-control-plane/
Popular repositories Loading
-
agent-control-plane
agent-control-plane PublicA credential is not authorisation. ACP moves the authorise/refuse decision for AI agent actions outside the model, where prompt injection cannot reach it. Specification, Dafny proofs, and a referen…
Python 7
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

